de.jungblut.online.regularization

Class AdaptiveFTRLRegularizer

java.lang.Object

de.jungblut.online.regularization.GradientDescentUpdater

de.jungblut.online.regularization.AdaptiveFTRLRegularizer

All Implemented Interfaces:

WeightUpdater

public class AdaptiveFTRLRegularizer
extends GradientDescentUpdater

Based on the paper: http://www.eecs.tufts.edu/~dsculley/papers/ad-click-prediction.pdf

Author:

thomas.jungblut

Constructor Summary

Constructors

Constructor and Description
AdaptiveFTRLRegularizer(double beta, double l1, double l2) Creates a new AdaptiveFTRLRegularizer.

Method Summary

Modifier and Type	Method and Description
CostWeightTuple	computeNewWeights(de.jungblut.math.DoubleVector theta, de.jungblut.math.DoubleVector gradient, double learningRate, long iteration, double lambda, double cost) Simplistic gradient descent without regularization.

Methods inherited from class de.jungblut.online.regularization.GradientDescentUpdater

computeGradient

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AdaptiveFTRLRegularizer

public AdaptiveFTRLRegularizer(double beta,
                               double l1,
                               double l2)

Creates a new AdaptiveFTRLRegularizer.

Parameters:

beta - the smoothing parameter for the learning rate.

l1 - the l1 regularization.

l2 - the l2 regularization.

Method Detail

computeNewWeights

public CostWeightTuple computeNewWeights(de.jungblut.math.DoubleVector theta,
                                         de.jungblut.math.DoubleVector gradient,
                                         double learningRate,
                                         long iteration,
                                         double lambda,
                                         double cost)

Description copied from class: GradientDescentUpdater

Simplistic gradient descent without regularization.

Specified by:

computeNewWeights in interface WeightUpdater

Overrides:

computeNewWeights in class GradientDescentUpdater

Parameters:

theta - the old weights.

gradient - the gradient.

learningRate - the learning rate.

iteration - the number of the current iteration.

lambda - the regularization parameter.

cost - the computed cost for this gradient update.

Returns:

the already updated weights for a particular updated gradient.